Data is a raw material for making informed decisions, answer critical questions and make it possible to gain competitive advantage. The considerable challenge facing both commercial and none profit organizations today is the explosion of data. Before using data, however, considerable effort and techniques must be applied to prepare data that will be ready for analysis. High quality data will result in high quality end product. Data will need to be formatted, statistically summarized, and graphically visualized and documented.

Gain Insights. Take Action.
Regardless of the industry or sector a customer fit, the modular data services listed below will benefit you by harnessing insight learned and pattern detected to make important decisions.

Request for a free consultation to start discussing your requirements and what you want to achieve. You will get a prompt response that include initial assessment, plan of action and deliverable timeline.

1. Data Cleaning and Prepration

Description:

Quality data is the most important aspect of data analytic. Starting from a raw data and gaining a dataset that is relevant, accurate and connected, literally determines the success or failure of the question a customer wants to answer or make decision on.

Key Capabilities:

  • Whether your data is structured or unstructured, industry best practice methods will be applied, and data carpentry best practices will be utilized to clean, wrangle and feature engineer your data to improve its quality.
  • Pull data that exist in different formats, such as R, Excel, MiniTab, STATA, SAS, SPSS, plain text, and blend them together to generate consistent dataset for smooth data exploration and analysis.
  • Use Application Programming Interface (API) to tap into data warehouses from US government (ex. US Census), international organizations (ex. UN/WHO/WB), Municipalities, national statistical associations (ex. Federal Reserve Bank of St. Louis - Economic Research County), and commercial entities to spawn high quality datasets.

2. Data driven Thematic and Geographic Maps

Description:

Visualizing data “involves the creation and study of the visual representation of data.”(Wikipedia) Applying statistical analysis to data and overlaying it on geographical maps like continents, countries, counties and cities “can help you make meaningful comparisons among thousands of pieces of information, extracting patterns not easily found through other methods.”

Key Capabilities:

  • Generate publication ready statistical data driven graphics, to help visualize quantitative information.
  • Build a interactive web graphic that can be inserted in a document or a web page.
  • Overlay shape and geojson files with Leaflet, a java Script based package that converts static maps into information rich interactive maps. A custom popup information displays can be added.
  • Capture, manipulate, analyze and present raw data, and generate a spatial analytic result in a context of cartographic maps.

3. Reproducible dynamic Automated Reporting

Description:

Data driven document is a very high quality document that includes interactive tables, figures, statistical graphs and geographic maps. Reproducibility is a requirement that validates studies and research papers. Which means, the data/codes used and plots/maps generated in the analysis should be replaceable to gain acceptance. The document has facility that will automatically update itself when underlying data for graphs and maps change, keeping the report accurate to the present.

Key Capabilities:

  • Use markdown to generate document that include interactivity plots, tables, graphs and maps that can be rendered in HTML, PDF and Word.
  • Choose and apply one of several themes that will enhance the look and feel of the document.
  • Generate an HTML5 slide presentation that can include options for slide transitions and slide navigation
  • Can be published as HTML file
  • Support for LaTeX equations using MathJax.
  • Ability to customize the appearance of slides using CSS.

4. Natural Langague processing

Description:

Natural language Processing (NLP) “is field of study that focuses on the interactions between human language and computers, and derive meaning from human language in a smart and useful way.” Organizations maintain most of their data in word and pdf documents written in a natural language, not in databases. It is one of the richest information set most organization’s posses, but rarely tap into to benefit from. Gaining access and insight to this information, utilizing analytical NLP packages, will bring tremendous valuable that will yield a competitive advantage.

Key Capabilities:

  • Key phrase extraction - Given a document, exploits structure of the words in the document, and determine “central” key phrase and output a list. Similar to Google PageRank selects Web pages.
  • Sentiment Analysis - excerpt subjective information from a document3, to determine sentiment. It is especially useful for identifying trends.
  • Optical character recognition (OCR) ingest - Given an image representing printed text, ingest and tidy text data and prepare for analysis.
  • Text summerization - and more.

5. Interactive Dashboard

Description:

Intuitive powerful web based dashboard that lets you interactively explore, manipulate, monitor and Visualize your data.

Key Capabilities:

6. Contact

Drop me email abiyu.giday@gmail.com or follow me on twitter @abiyugiday, send me friend request on linkedin and don’t forget to check my blog with new updates abiyug.github.io.